Triple
T7327892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sogdian alphabet |
E168919
|
entity |
| Predicate | iso15924Code |
P11937
|
FINISHED |
| Object | Sogd |
E120202
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sogd | Statement: [Sogdian alphabet, iso15924Code, Sogd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sogd Context triple: [Sogdian alphabet, iso15924Code, Sogd]
-
A.
Sogdia
Sogdia was an ancient Iranian-speaking region in Central Asia, renowned as a key hub of trade and culture along the Silk Road.
-
B.
Sogdians
chosen
The Sogdians were an ancient Iranian people of Central Asia renowned as influential Silk Road merchants and cultural intermediaries between East and West.
-
C.
Kharas
Kharas is a Palestinian village located in the Hebron Governorate in the southern West Bank.
-
D.
Khwarezm
Khwarezm is a historic region in Central Asia, centered around the lower Amu Darya river, that served as an important cultural and political hub for various Iranian and Turkic peoples over many centuries.
-
E.
Transcaspia
Transcaspia was a historical region in Central Asia, largely corresponding to modern-day Turkmenistan, that lay east of the Caspian Sea and was once part of the Russian Empire.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c68a54cacc81908e3b773441f19566 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0a879b88190bef0fb6cbae411ff |
completed | March 27, 2026, 9:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7fa7f71888190a5025355c303c41d |
completed | March 28, 2026, 3:57 p.m. |
Created at: March 27, 2026, 3:03 p.m.